我有以下表结构：
CREATE TABLE mytable (
id serial PRIMARY KEY,
data jsonb
);
以下数据（部分为了简洁起见......注意年份的随机性和销售/费用彼此不一致）：
INSERT INTO mytable (data)
VALUES
('{"employee": "Jim Romo",
"sales": [{"value": 10, "yr": "2012"}, {"value": 5, "yr": "2013"}, {"value": 40, "yr": "2014"}],
"expenses": [{"value": 2, "yr": "2007"}, {"value": 1, "yr": "2013"}, {"value": 3, "yr": "2014"}],
"product": "tv", "customer": "1", "updated": "20150501"
}'),
('{"employee": "Jim Romo",
"sales": [{"value": 10, "yr": "2012"}, {"value": 5, "yr": "2013"}, {"value": 41, "yr": "2014"}],
"expenses": [{"value": 2, "yr": "2009"}, {"value": 3, "yr": "2013"}, {"value": 3, "yr": "2014"}],
"product": "tv", "customer": "2", "updated": "20150312"
}'),
('{"employee": "Jim Romo",
"sales": [{"value": 20, "yr": "2012"}, {"value": 25, "yr": "2013"}, {"value": 33, "yr": "2014"}],
"expenses": [{"value": 8, "yr": "2012"}, {"value": 12, "yr": "2014"}, {"value": 5, "yr": "2009"}],
"product": "radio", "customer": "2", "updated": "20150311"
}'),
('{"employee": "Bill Baker",
"sales": [{"value": 1, "yr": "2010"}, {"value": 2, "yr": "2009"}, {"value": 3, "yr": "2014"}],
"expenses": [{"value": 3, "yr": "2011"}, {"value": 1, "yr": "2012"}, {"value": 7, "yr": "2013"}],
"product": "tv", "customer": "1", "updated": "20150205"
}'),
('{"employee": "Bill Baker",
"sales": [{"value": 10, "yr": "2010"}, {"value": 12, "yr": "2011"}, {"value": 3, "yr": "2014"}],
"expenses": [{"value": 4, "yr": "2011"}, {"value": 7, "yr": "2009"}, {"value": 4, "yr": "2013"}],
"product": "radio", "customer": "1", "updated": "20150204"
}'),
('{"employee": "Jim Romo",
"sales": [{"value": 22, "yr": "2009"}, {"value": 17, "yr": "2013"}, {"value": 35, "yr": "2014"}],
"expenses": [{"value": 14, "yr": "2011"}, {"value": 13, "yr": "2014"}, {"value": 8, "yr": "2013"}],
"product": "tv", "customer": "3", "updated": "20150118"
}')
对于每位员工，我需要评估最近更新的行，并找到2014年电视销售额超过30的员工。从那里我需要进一步筛选平均电视费用低于5的员工。平均而言我只是需要承担他们所有的电视费用，而不仅仅是最新一行。
我的预期输出为1行：
employee | customer | 2014 tv sales | 2013 avg tv expenses
------------+----------+-----------------+----------------------
Jim Romo | 1 | 40 | 4
我可以（有点）做1或其他但不是两者：
一个。获得2014年销售＆gt; 30（但无法获得他们最近的＆＃34;电视＆＃34;销售;（
SELECT * FROM mytable WHERE (SELECT (a->>'value')::float FROM
(SELECT jsonb_array_elements(data->'sales') as a) as b
WHERE a @> json_object(ARRAY['yr', '2014'])::jsonb) > 30
湾获得平均2013年费用（这需要平均电视费用）
SELECT avg((a->>'value')::numeric) FROM
(SELECT jsonb_array_elements(data->'expenses') as a FROM mytable) as b
WHERE a @> json_object(ARRAY['yr', '2013'])::jsonb
编辑：这可能是一个非常大的表，所以任何关于性能和索引需求的评论都会受到赞赏，因为我是postgresql和jsonb的新手。
编辑＃2：我已经尝试了两个答案，对于一张大桌子来说似乎都没有效率;（答案 0 :(得分：1)
这是对您的问题的（相当冗长的）答案。查询中的注释应该解释不同的部分。我遵循的基本思路是：1）保持每个操作的简单，首先尝试产生正确的结果，然后进行优化; 2）尽可能多地（但不是很多）改变json结构中的更多＆＃34;关系类似＆＃34;结构，因为关系有更强大的运算符，json数据在postgres中。 Corse中有空间来简化查询，甚至可以生成更高效的版本，但至少这是一个起点。
with mytable1 as -- transform the table in a more "relational-like" structure (just for clarity)
(select id, data->>'employee' as employee, data->>'product' as product,
(data->>'updated')::integer as updated, (data->>'customer')::integer as customer,
data->'sales' as sales, data->'expenses' as expenses
from mytable),
avg_exp_for_2013_tv as -- find the average expenses for tv in 2013 for each employee
(select employee, avg(expenses.value) as avg2013_expenses
from mytable1 , jsonb_to_recordset(expenses) as expenses(yr text, value float)
where product = 'tv' and expenses.yr = '2013'
group by employee),
most_recent_updates_employees as -- find the most recent updates for each employee
(select employee, max(updated) as updated
from mytable1 t1
group by employee),
most_recent_updated_rows as -- find the rows with the most recent updates
(select t1.*
from mytable1 t1, most_recent_updates_employees m
where t1.employee = m.employee and t1.updated = m.updated),
employees_with_2014_tv_sales_gt_30 as
(select employee, customer, sales.value as sales_value
from most_recent_updated_rows m, jsonb_to_recordset(m.sales) as sales(yr text, value float)
where yr = '2014' and value > 30)
select e1.employee, e1.customer, e1.sales_value as "2014 tv sales", e2.avg2013_expenses as "2013 avg tv expenses"
from employees_with_2014_tv_sales_gt_30 e1, avg_exp_for_2013_tv e2
where e1.employee = e2.employee and avg2013_expenses < 5
答案 1 :(得分：0)
解压缩多级jsons的最佳方法是逐步为每个级别和每个数组构建记录，在途中选择所需的值。 这样您就可以获得一个漂亮的逻辑分层查询。在问题中描述的情况下，您需要两个连接的查询，因为其中一个必须计算另一个条件下的值的平均值。
select distinct on (employee) employee, customer, sales_2014, avg_expenses_2013::numeric(20,2)
from (
select s.employee, customer, updated, sales_2014, avg_expenses_2013
from (
select employee, customer, updated, (sales->>'value')::int sales_2014
from (
select employee, customer, updated, jsonb_array_elements(sales) sales
from (
select c.*
from
mytable,
jsonb_to_record(data)
as c(employee text, product text, customer text, updated text, sales jsonb)
) alias
where product = 'tv'
) alias
where sales->>'yr' = '2014'
) s
join (
select employee, avg((expenses->>'value')::numeric) avg_expenses_2013
from (
select employee, jsonb_array_elements(expenses) expenses
from (
select c.*
from
mytable,
jsonb_to_record(data)
as c(employee text, product text, expenses jsonb)
) alias
where product = 'tv'
) alias
where expenses->>'yr' = '2013'
group by 1
) e
on s.employee = e.employee
where sales_2014 > 30
) alias
order by employee, updated desc;
employee | customer | sales_2014 | avg_expenses_2013
------------+----------+------------+-------------------
Jim Romo | 1 | 40 | 4.00
(1 row)
即使使用像索引这样的优化，大型表上的查询性能也会非常令人失望。如果您必须对此数据进行此类分析，则应重新考虑数据模型，该模型设计不当用于此目的。我遗漏了一些负责任地提出适当变更的关键信息：
然而，有一件事似乎是肯定的。您应该将json数据解压缩到具有常规类型列的规范化表中。该模型可能如下所示：
create table employees (
employee_id serial primary key,
employee_name text);
create table reports ( -- stipulated name of rows of your table
report_id serial primary key,
employee_id int references employees,
product_name text, -- product_id references products?
cutomer_no int, -- customer_id references customers?
updated_at date);
create table sales (
sale_id serial primary key,
report_id int references reports,
year_no int;
total int); -- numeric?
create table expenses (
expense_id serial primary key,
report_id int references reports,
year_no int;
total int);